Digital model construction method of urban area building structure based on three-dimensional oblique photography

Abstract

The invention provides a digital model construction method for an urban area building structure based on three-dimensional oblique photography, and the method comprises the steps: obtaining high-definition image data through employing a three-dimensional oblique photography technology, and taking the high-definition image data as an input image; preprocessing the input image to obtain a preprocessed image; calculating shallow layer features of the preprocessed image through a feature encoder; convolution is carried out on the preprocessed image by using hole convolution to obtain depth features; performing feature fusion on the shallow feature and the depth feature through a feature decoder to obtain a fused feature; constructing contour information of the building according to the fusion features, and calculating geometric structure information of the building structure; a digital model is constructed based on the contour information and the geometry information. The technical problems that a traditional urban area building structure digital model construction method needs a large amount of manpower and material resources, consumes long time and is high in cost, and the real structure and details of the building cannot be completely restored can be solved.

Description

Technical Field

[0001] The present application relates to the technical field of digital modeling and urban planning, and in particular to a method for constructing a digital model of an urban area building structure based on three-dimensional oblique photography. Background Art

[0002] With the continuous development of science and technology, the application of digital models in urban planning, land use evaluation, landscape design and other aspects is becoming more and more extensive, making the construction of digital models of urban area building structures an important work content in urban planning, land use evaluation, landscape design and other fields.

[0003] Traditional digital modeling methods mainly include laser scanning, manual modeling, and satellite image modeling. These methods can meet the needs of modeling to a certain extent, but there are some problems. First, although laser scanning technology can accurately obtain the structural information of buildings, it is costly, labor-intensive, and time-consuming, and is not suitable for modeling large-scale urban areas. Manual modeling requires a lot of manpower and material resources, is time-consuming and labor-intensive, and has limited accuracy. Satellite image modeling has the advantages of a wide range of modeling and fast speed, but its disadvantage is that the resolution is low and the detailed structure of the building cannot be accurately restored. Summary of the invention

[0004] The present application provides a method for constructing a digital model of an urban area building structure based on three-dimensional oblique photography, so as to solve the technical problems that the traditional method for constructing a digital model of an urban area building structure requires a lot of manpower and material resources, is time-consuming and costly, and cannot fully restore the real structure and details of the building.

[0005] The present application provides a method for constructing a digital model of an urban area building structure based on three-dimensional oblique photography, comprising:

[0006] Use three-dimensional oblique photography technology to obtain high-resolution image data as input images;

[0007] Preprocessing the input image to obtain a preprocessed image;

[0008] Calculate shallow features of the preprocessed image through the feature encoder;

[0009] Use dilated convolution to convolve the preprocessed image to obtain deep features;

[0010] The shallow features and deep features are fused through the feature decoder to obtain fused features;

[0011] Construct the building's outline information based on the fused features and calculate the building's geometric structure information;

[0012] A digital model is constructed based on contour information and geometric structure information.

[0013] Optionally, use 3D oblique photography technology to obtain high-resolution image data, including:

[0014] Using three-dimensional oblique photography technology, high-definition photography equipment is installed on drones or fixed-wing aircraft to perform multi-angle shooting to obtain high-definition image data.

[0015] Optionally, preprocess the input image to obtain a preprocessed image, including:

[0016] Perform non-local mean denoising on the input image and calculate the local Gaussian weight of the input image.

[0017]

[0018] in, Represents the position within the input image The pixel value of the pixel at Represents the position within the input image The pixel value of the pixel at and Respectively and The translation values ​​in the horizontal and vertical directions, Indicates location The horizontal and vertical directions are respectively and After the position, represents the standard deviation of the Gaussian kernel, represents the exponential function, express and The local Gaussian weights between

[0019] The input image is denoised by non-local mean through local Gaussian weights to obtain the denoised image.

[0020]

[0021] in, represents the denoised image, Represents the position within the input image The pixel value of the pixel at Represents the position within the input image The pixel value of the pixel at and Respectively and The translation values ​​in the horizontal and vertical directions, Indicates location The horizontal and vertical directions are respectively and After the position, represents the denoising factor, , used to adjust the denoising strength, express and The local Gaussian weights between

[0022] Perform nonlinear color correction on the denoised image to obtain the preprocessed image.

[0023]

[0024] in, Represents a nonlinear perception factor, which is used to adjust the image color deviation. represents the denoised image, represents the preprocessed image, that is, the image after nonlinear color correction.

[0025] Optionally, in calculating the shallow features of the preprocessed image by the feature encoder, the shallow features are:

[0026]

[0027] in, Represents shallow features, represents the preprocessed image, that is, the image after nonlinear color correction, Represents the preprocessed image Location within The pixel value of the pixel at Represents the preprocessed image Location The pixel value of the pixel at and Respectively and The translation values ​​in the horizontal and vertical directions, Indicates location The horizontal and vertical directions are respectively and After the position, Represents the penalty factor, used to adjust the position The influence of the characteristics between represents the calculation of gradient, Represents the pixel density function, used to calculate the position With location The pixel difference between Indicates location With location The Euclidean distance between Represents an exponential function.

[0028] Optionally, in the process of convolving the preprocessed image using the dilated convolution to obtain the deep features, the deep features are:

[0029]

[0030] in, represents the deep features, Indicates the size The convolution kernel, represents the preprocessed image, that is, the image after nonlinear color correction, r represents the dilation rate in the dilated convolution, Represents the convolution kernel The size in the horizontal direction, Represents the convolution kernel The size in the vertical direction, Represents the preprocessed image Location within The pixel value of the pixel at .

[0031] Optionally, in the fusion feature obtained by fusing the shallow feature with the deep feature through the feature decoder, the fusion feature is:

[0032]

[0033] in, Represents the feature fusion operation.

[0034] Optionally, the building outline information is constructed based on the fused features, and the geometric structure information of the building structure is calculated, including:

[0035] The feature decoder processes the fused features to construct the building's contour information, and obtains the contour information map after image reconstruction:

[0036]

[0037] in, Represents the contour information map after image reconstruction, represents the shallow features calculated by the feature encoder, represents the deep features obtained by dilated convolution, represents the fusion feature, represents the calculation of gradient, represents the projection reconstruction function, and represents the characteristic integral parameter;

[0038] The geometric structure information of the building structure is calculated according to the outline information of the building, and the geometric structure information includes the length, width and height of the building structure.

[0039] Optionally, the geometric structure information of the building structure is calculated based on the outline information of the building, including:

[0040] Select a reference object with known geometric structure information near the building structure;

[0041] Measure pixel distances to reference objects in images;

[0042] Dividing the actual geometric structure information of the reference object and the pixel distance of the reference object in the image respectively, to obtain a proportional factor between the actual geometric structure information and the pixel distance;

[0043] The pixel distance in the building's outline information is multiplied by the scale factor to calculate the actual geometric structure information of the building.

[0044] Correspondingly, the present application also provides an electronic device, which includes a memory and a processor, the memory being used to store executable program code; the processor being connected to the memory, and running a computer program corresponding to the executable program code by reading the executable program code, so as to execute the aforementioned method for constructing a digital model of an urban area building structure based on three-dimensional oblique photography.

[0045] Accordingly, the present application also provides a digital model construction system for urban area building structures based on three-dimensional oblique photography, which includes the aforementioned electronic device.

[0046] This application provides a method for constructing a digital model of an urban area building structure based on three-dimensional oblique photography. The method achieves accurate restoration of the urban building structure through three-dimensional oblique photography technology and digital modeling technology, reduces manpower and time costs, and improves modeling efficiency. At the same time, the digital modeling has high accuracy and rich details, which meets the requirements of urban planning and design fields for model accuracy and authenticity, helps to improve the level of planning and design work, and promotes the development of urban planning and design fields. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 It is a flow chart of a method for constructing a digital model of an urban area building structure based on three-dimensional oblique photography provided by the present application;

[0049] Figure 2 It is a flowchart of step S200 in the method for constructing a digital model of an urban area building structure based on three-dimensional oblique photography provided by the present application. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application. In addition, it should be understood that the specific implementation methods described herein are only used to illustrate and explain the present application and are not used to limit the present application. In the present application, unless otherwise stated, the directional words used, such as "up", "down", "left", and "right", generally refer to the up, down, left, and right of the device in actual use or working state, specifically the drawing direction in the accompanying drawings.

[0051] The present application provides a method for constructing a digital model of an urban area building structure based on three-dimensional oblique photography, which is described in detail below. It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments of the present application. In the following embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0052] See also Figure 1 and Figure 2 The present application provides a method for constructing a digital model of an urban area building structure based on three-dimensional oblique photography. The method first uses three-dimensional oblique photography technology to obtain multi-angle, high-definition image data of the urban area; secondly, the obtained image data is processed through image processing, and then, the digital model is used to accurately restore the urban building structure, thereby providing visualization support for urban planning, land use evaluation, landscape design, etc.

[0053] Compared with the traditional method of constructing digital models of urban regional building structures, this method has the following advantages: first, it reduces labor costs and time costs and improves modeling efficiency; second, the image data obtained through three-dimensional oblique photography technology is more real and comprehensive, and can accurately restore the building structure; third, the digital modeling has high accuracy and rich details, which can meet the requirements of urban planning, design and other fields for model accuracy and authenticity. Therefore, this method is of great significance for improving the work efficiency and accuracy in urban planning, land use evaluation, landscape design and other fields, and is expected to be widely used in architectural design, urban planning and other fields.

[0054] See also Figure 1 and Figure 2 The method for constructing a digital model of an urban area building structure based on three-dimensional oblique photography specifically includes the following steps:

[0055] S100, using three-dimensional oblique photography technology to obtain high-definition image data as an input image;

[0056] In step S100, three-dimensional oblique photography technology is used to perform multi-angle shooting by using a drone or fixed-wing aircraft equipped with high-definition photography equipment to obtain high-definition image data.

[0057] With the development of 3D oblique photography technology, its application in urban planning, environmental monitoring, geographic information systems and other fields is becoming more and more extensive. 3D oblique photography technology can record urban landscape and building structure information in an all-round and high-definition manner by acquiring multi-angle images of buildings at the same time, providing new ideas and methods for the construction of digital models of urban area building structures.

[0058] The digital model construction method of urban area building structure obtains high-definition image data based on three-dimensional oblique photography technology. On the one hand, it can obtain building structure information more comprehensively and accurately, and can realize the accurate restoration of urban building structure; on the other hand, it can significantly reduce the manpower and time cost of modeling and improve modeling efficiency.

[0059] S200, preprocessing the input image to obtain a preprocessed image;

[0060] The collected image data is pre-processed, including denoising and chromatic aberration correction, to improve image quality.

[0061] Step S200 specifically includes the following steps:

[0062] S210, performing non-local mean denoising processing on the input image, calculating the local Gaussian weight of the input image,

[0063]

[0064] in, Represents the position within the input image The pixel value of the pixel at Represents the position within the input image The pixel value of the pixel at and Respectively and The translation values ​​in the horizontal and vertical directions, Indicates location The horizontal and vertical directions are respectively and After the position, represents the standard deviation of the Gaussian kernel, represents the exponential function, express and The local Gaussian weights between .

[0065] S220, performing non-local mean denoising on the input image by using local Gaussian weights to obtain a denoised image,

[0066]

[0067] in, represents the denoised image, Represents the position within the input image The pixel value of the pixel at Represents the position within the input image The pixel value of the pixel at and Respectively and The translation values ​​in the horizontal and vertical directions, Indicates location The horizontal and vertical directions are respectively and After the position, represents the denoising factor, , used to adjust the denoising strength, express and The local Gaussian weights between .

[0068] S230, performing nonlinear color correction on the denoised image to obtain a preprocessed image, that is, an image after nonlinear color correction, to correct the image color deviation caused by shooting conditions, device characteristics or other factors.

[0069]

[0070] in, Represents a nonlinear perception factor, which is used to adjust the image color deviation. represents the denoised image, represents the preprocessed image, that is, the image after nonlinear color correction.

[0071] S300, calculating the shallow features of the denoised image through a feature encoder, the shallow features are:

[0072]

[0073] in, Represents shallow features, represents the preprocessed image, that is, the image after nonlinear color correction, Represents the preprocessed image Location within The pixel value of the pixel at Represents the preprocessed image Location The pixel value of the pixel at and Respectively and The translation values ​​in the horizontal and vertical directions, Indicates location The horizontal and vertical directions are respectively and After the position, Represents the penalty factor, used to adjust the position The influence of the characteristics between represents the calculation of gradient, Represents the pixel density function, used to calculate the position With location The pixel difference between Indicates location With location The Euclidean distance between Represents an exponential function.

[0074] S400, convolve the denoised image using a dilated convolution to obtain a depth feature, the depth feature is:

[0075]

[0076] in, represents the deep features, Indicates the size The convolution kernel, represents the preprocessed image, that is, the image after nonlinear color correction, r represents the dilation rate in the dilated convolution, Represents the convolution kernel The size in the horizontal direction, Represents the convolution kernel The size in the vertical direction, Represents the preprocessed image Location within The pixel value of the pixel at .

[0077] S500, the shallow features and the deep features are fused by the feature decoder to obtain fused features, and the fused features are:

[0078]

[0079] in, Represents the feature fusion operation.

[0080] The shallow features of the image are calculated through the feature encoder. The shallow features usually contain detailed information such as the edge and texture of the image, providing a basis for subsequent processing. The image is convolved using the dilated convolution to obtain the deep features of the image. The deep features contain more abstract semantic information to obtain a richer image feature representation. The shallow features and deep features are fused through the feature decoder to obtain the fused features. The fused features can use both types of information at the same time, thereby enhancing the model's ability to express the complexity of the building structure to obtain a more comprehensive and rich feature representation. Therefore, the digital modeling has high accuracy and rich details, which meets the requirements of urban planning and design fields for model accuracy and authenticity, and helps to improve the level of planning and design work.

[0081] Since the fused features can better reflect the geometric shape and boundaries of the building, the contour detection algorithm can more accurately locate the edge of the building. Therefore, after feature fusion, the model can more accurately identify the outline of the building. At the same time, due to the fusion of feature information at different levels, the model can more accurately capture the edges and details of the building, so the fused features can improve the recognition accuracy of the building outline. Through feature fusion, the model can build a more sophisticated and realistic digital model, including the subtle structure and texture information of the building.

[0082] The fusion features provide a richer source of information for the calculation of geometric structure information, including not only the plane layout of the building, but also three-dimensional information such as height and volume. With this information, the geometric structure of the building can be calculated more accurately, providing accurate data support for the construction of the digital model, which helps the model to more comprehensively understand and express the structural and texture characteristics of the building.

[0083] The fused features make the model more robust to adverse factors such as illumination changes, occlusion and noise.

[0084] S600: Constructing the outline information of the building according to the fused features, and calculating the geometric structure information of the building structure.

[0085] Step S600 specifically includes the following steps:

[0086] S610, processing the fused features through a feature decoder to construct the contour information of the building, and obtaining a contour information map after image reconstruction:

[0087]

[0088] in, Represents the contour information map after image reconstruction, represents the shallow features calculated by the feature encoder, represents the deep features obtained by dilated convolution, represents the fusion feature, represents the calculation of gradient, represents the projection reconstruction function, and represents the characteristic integral parameter;

[0089] and Represents the feature integral parameter, the purpose of which is to calculate the overall contour information of the feature. The integral can be used to capture the edge or contour information of the image or the edge or contour information of a partial area in the image.

[0090] S620: Calculate geometric structure information of the building structure according to the outline information of the building. The geometric structure information includes but is not limited to the length, width, and height of the building structure.

[0091] In step S620, the actual geometric structure information of the building is calculated by comparing the proportional relationship between the pixel distance of the building in the image and the actual size.

[0092] Step S620 specifically includes the following steps:

[0093] S621, selecting a reference object with known geometric structure information near the building structure;

[0094] The reference object may be any object with known dimensions, such as a standard sidewalk, a road sign, a portion of a building (eg, a window), or any other object of standard dimensions, and the actual geometric information (eg, height) of the reference object may be known.

[0095] S622, measuring the pixel distance of the reference object in the image;

[0096] The pixel distance (length) of a reference object measured in an image can usually be determined by calculating the pixel distance between two endpoints in the image.

[0097] S623, dividing the actual geometric structure information of the reference object and the pixel distance of the reference object in the image respectively to obtain a proportional factor between the actual geometric structure information and the pixel distance;

[0098] The scale factor may reflect the conversion coefficient between the actual size of the reference object and the image size.

[0099] S624: Multiply the pixel distance in the building's outline information by the scale factor to calculate the actual geometric structure information of the building.

[0100] For example, by multiplying the pixel length of a building in the image by the scale factor calculated above, the actual height of the building can be obtained, and the actual height unit can be adjusted according to the unit of the reference object. That is, the pixel distance in the building's outline information can be converted into the actual geometric size using the scale factor. This means that for the pixel distance in the outline information of any building measured in the image, its actual size in the real world can be obtained by multiplying it by the scale factor.

[0101] This method significantly improves the accuracy of building size recovery through precise measurement and calculation of scale factors, ensuring the dimensional consistency between the digital model and the actual building.

[0102] Through automated scale factor calculation and pixel distance conversion, the need for manual measurement is reduced, improving the automation and efficiency of the modeling process.

[0103] Accurate geometric structure information makes the digital model more realistic in visualization, providing high-quality visual reference for fields such as urban planning and architectural design.

[0104] Through accurate three-dimensional models, users can better understand the urban spatial structure and provide a more comprehensive spatial cognition for urban planning and architectural design.

[0105] S700: construct a digital model based on the contour information and the geometric structure information.

[0106] Using contour information, the exterior surface of a building can be accurately reconstructed. This includes the exact location and shape of all building elements such as windows, doors, and roofs. Geometric information provides the size and shape of the building, allowing the digital model to accurately reflect the height, width, and depth of the building. Combining contour and geometric information, each part of the building can be accurately located in three-dimensional space, ensuring that the spatial layout of the model is consistent with reality. When building a digital model, image texture and material information can be mapped to the corresponding surface of the model to increase the realism and visual details of the model. Using geometric information, the shadow effect of the building under different lighting conditions can be simulated, enhancing the dynamic sense and environmental adaptability of the model. For buildings with complex structures, such as multiple floors, irregular shapes, etc., geometric information can help the model accurately express these complexities. The constructed digital model is usually highly interactive, and users can observe and analyze the building from different angles and perspectives.

[0107] The method for constructing digital models of urban area building structures based on three-dimensional oblique photography technology has the following advantages: first, it can obtain more comprehensive and accurate building structure information, and can achieve accurate restoration of urban building structures; second, compared with traditional modeling methods, it greatly reduces the manpower and time costs of modeling and improves modeling efficiency; third, digital modeling has high accuracy and rich details, which can meet the requirements of urban planning, design and other fields for model accuracy and authenticity.

[0108] S800, integrate the constructed digital model into urban planning, land use evaluation, landscape design and other systems to provide visualization support using the digital model to assist decision making and program design.

[0109] The present application also provides a digital model construction system for urban area building structures based on three-dimensional oblique photography, which includes an electronic device. The electronic device includes a memory and a processor, the memory is used to store executable program codes; the processor is connected to the memory, and runs a computer program corresponding to the executable program code by reading the executable program code to execute the aforementioned digital model construction method for urban area building structures based on three-dimensional oblique photography.

[0110] The above is a detailed introduction to the method and system for constructing a digital model of urban area building structures based on three-dimensional oblique photography provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for constructing a digital model of an urban area building structure based on three-dimensional oblique photography, characterized in that: include: Use three-dimensional oblique photography technology to obtain high-resolution image data as input images; Preprocessing the input image to obtain a preprocessed image; Calculate shallow features of the preprocessed image through the feature encoder; Use dilated convolution to convolve the preprocessed image to obtain deep features; The shallow features and deep features are fused through the feature decoder to obtain fused features; Construct the building's outline information based on the fused features and calculate the building's geometric structure information; A digital model is constructed based on contour information and geometric structure information.

2. The method for constructing a digital model of an urban area building structure based on three-dimensional oblique photography according to claim 1, characterized in that: Use 3D oblique photography technology to obtain high-resolution image data, including: Using three-dimensional oblique photography technology, high-definition photography equipment is installed on drones or fixed-wing aircraft to perform multi-angle shooting to obtain high-definition image data.

3. The method for constructing a digital model of an urban area building structure based on three-dimensional oblique photography according to claim 1, characterized in that: Preprocess the input image to obtain a preprocessed image, including: Perform non-local mean denoising on the input image and calculate the local Gaussian weight of the input image. ； in, Represents the position within the input image The pixel value of the pixel at Represents the position within the input image The pixel value of the pixel at and Respectively and The translation values ​​in the horizontal and vertical directions, Indicates location The horizontal and vertical directions are respectively and After the position, represents the standard deviation of the Gaussian kernel, represents the exponential function, express and The local Gaussian weights between The input image is denoised by non-local mean through local Gaussian weights to obtain the denoised image. ； in, represents the denoised image, represents the denoising factor, , used to adjust the denoising strength; Perform nonlinear color correction on the denoised image to obtain the preprocessed image. ； in, Represents a nonlinear perception factor, which is used to adjust the image color deviation. represents the preprocessed image, that is, the image after nonlinear color correction.

4. The method for constructing a digital model of an urban area building structure based on three-dimensional oblique photography according to claim 1 or 3, characterized in that: In calculating the shallow features of the preprocessed image through the feature encoder, the shallow features are: ； in, Represents shallow features, represents the preprocessed image, Represents the preprocessed image Location within The pixel value of the pixel at Represents the preprocessed image Location The pixel value of the pixel at and Respectively and The translation values ​​in the horizontal and vertical directions, Indicates location The horizontal and vertical directions are respectively and After the position, Represents the penalty factor, used to adjust the position The influence of the characteristics between represents the calculation of gradient, Represents the pixel density function, used to calculate the position With location The pixel difference between Indicates location With location The Euclidean distance between Represents an exponential function.

5. The method for constructing a digital model of an urban area building structure based on three-dimensional oblique photography according to claim 4, characterized in that: When convolving the preprocessed image with a dilated convolution to obtain the deep features, the deep features are: ； in, represents the deep features, Indicates the size The convolution kernel of , r represents the dilation rate in the dilated convolution, Represents the convolution kernel The size in the horizontal direction, Represents the convolution kernel The size in the vertical direction, Represents the preprocessed image Location within The pixel value of the pixel at .

6. The method for constructing a digital model of an urban area building structure based on three-dimensional oblique photography according to claim 5, characterized in that: When the shallow features and deep features are fused through the feature decoder to obtain the fused features, the fused features are: ； in, represents the fusion feature, Represents the feature fusion operation.

7. The method for constructing a digital model of an urban area building structure based on three-dimensional oblique photography according to claim 6, characterized in that: The building outline information is constructed based on the fused features, and the geometric structure information of the building structure is calculated, including: The fused features are processed by the feature decoder to construct the contour information of the building, and the contour information map after image reconstruction is obtained: ； in, Represents the contour information map after image reconstruction, represents the calculation of gradient, represents the projection reconstruction function, and represents the characteristic integral parameter; The geometric structure information of the building structure is calculated according to the outline information of the building, and the geometric structure information includes the length, width and height of the building structure.

8. The method for constructing a digital model of an urban area building structure based on three-dimensional oblique photography according to claim 7, characterized in that: Calculate the geometric structure information of the building structure based on the building's outline information, including: Select a reference object with known geometric structure information near the building structure; Measure pixel distances to reference objects in images; Dividing the actual geometric structure information of the reference object and the pixel distance of the reference object in the image respectively, to obtain a proportional factor between the actual geometric structure information and the pixel distance; The pixel distance in the building's outline information is multiplied by the scale factor to calculate the actual geometric structure information of the building.

Images